AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Von Mises-Fisher Mixture Model with Dynamic Shrinkage for Realistic Test-Time Transduction

Jiazhen Huang, Zhiming Liu, Changhu Wang, Wei Ju, Ziyue Qiao, Xiao Luo

ICML 2026 · Label-efficient and robust learning › Test-time adaptation · approach: Test-time adaptation of vision-language models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add alpha dynamic shrinkage (ablation)Ours · Component ablation, bs 64 and 1000accuracy: 69.0 -> 72.4 (Bs=64); 68.9 -> 71.1 (Bs=1,000)Improved
add gamma instance weighting (ablation)Ours · Component ablation, bs 64 and 1000accuracy: 72.3 -> 72.4 (Bs=64); 70.4 -> 71.1 (Bs=1,000)Mixed
add iterative update of mu (ablation)Ours · Component ablation, bs 64 and 1000accuracy: 66.8 -> 72.4 (Bs=64); 66.5 -> 71.1 (Bs=1,000)Improved
add iterative update of kappa (ablation)Ours · Component ablation, bs 64 and 1000accuracy: 70.8 -> 72.4 (Bs=64); 68.9 -> 71.1 (Bs=1,000)Improved
set alpha_k = 1/lambda_k instead of lambda_k (ablation)Ours · Medium, bs 1000, ImageNetaccuracy: 68.5 -> 81.6Improved
set alpha_k = 1/lambda_k instead of lambda_k (ablation)Ours · Medium, bs 1000, averageaccuracy: 67.6 -> 72.9Improved
set alpha_k = 1/lambda_k instead of exp(-lambda_k) (ablation)Ours · Medium, bs 1000, averageaccuracy: 68.8 -> 72.9Improved
use geometric mean for lambda_k instead of arithmetic mean (ablation)Ours · Extreme imbalance, avgaccuracy: 73.9 -> 73.1Hurt
use geometric mean for lambda_k instead of arithmetic mean (ablation)Ours · Mild imbalance, avgaccuracy: 67.8 -> 68.4Improved
use geometric mean for lambda_k instead of max only (ablation)Ours · Extreme imbalance, avgaccuracy: 71.4 -> 73.1Improved
replace GMM in StatA with vMF mixture (ablation)StatA · Batch adaptation avg, bs 64accuracy: 69.01 -> 68.69Hurt
replace Gaussian with vMF mixture (ablation)Ours · Batch adaptation avg, bs 64accuracy: 71.49 -> 72.36No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy